Initial: integrated 2025 LawGraph (graphrag_pipeline) + 2026 kg_project

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

dofile/kg_project/config/deep_extraction_config.yaml

@@ -0,0 +1,122 @@
+llm:
+  model: "deepseek-chat"
+  temperature: 0.0
+  max_tokens: 8192
+  max_retries: 3
+  retry_delay: 2
+  request_timeout: 120
+  batch_timeout: 600
+
+batch_processing:
+  batch_size: 10
+  concurrent_requests: 5
+  test_batch_size: 5
+  incremental_save: true
+
+deduplication:
+  similarity_threshold: 0.85
+  enable_fuzzy_matching: true
+  text_normalization: true
+
+validation:
+  enable_entity_validation: true
+  enable_relationship_validation: true
+  min_confidence_score: 0.7
+  strict_mode: false
+  filter_generic_concepts: true
+
+output:
+  nodes_file: "output/nodes_llm_v2.csv"
+  relationships_file: "output/rels_llm_v2.csv"
+  report_file: "output/extraction_report_v2.md"
+  encoding: "utf-8-sig"
+
+progress:
+  progress_file: "output/progress_v2.json"
+  checkpoint_interval: 10
+
+logging:
+  log_file: "logs/deep_extraction_v2.log"
+  level: "INFO"
+  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+
+# ============================================================
+# 第二轮本体：城市更新法规政策工具箱 (21实体 + 34关系)
+# ============================================================
+
+entity_type_prompts:
+  Agency: "主体机构：发布主体、实施主体、监管主体、责任主体，包括政府部门（全国人大常委会、国务院、自然资源部、住建部、生态环境部、发改委、地方政府）、实施机构、平台公司、社区组织、第三方机构等。属性：level（国家/省级/市级/县级/乡镇街道/社区）、agency_type（立法机关/行政机关/主管部门/实施主体/监管主体/责任主体/市场主体/社区组织/第三方机构）"
+  LegalObject: "法规事项：法规政策所规制的事项，回答'管什么事项'。如规划编制、土地利用、建设管理、历史文化保护、生态保护、财政支持、金融支持、产权登记、公众参与、行政审批、监督管理、城市更新、公共服务、基础设施、安全韧性等。属性：category"
+  SpatialObject: "空间对象：城市更新中的具体空间对象，回答'作用于什么空间'。如老旧小区、城中村、低效用地、工业遗存、历史文化街区、历史建筑、公共空间、公共服务设施、市政基础设施、存量建筑、建设用地、城市更新单元、生态保护红线、永久基本农田、城镇开发边界等。属性：spatial_type"
+  RenewalScene: "更新场景：城市更新应用场景，回答'用于什么更新场景'。如老旧小区改造、城中村改造、低效用地再开发、工业遗存更新、历史文化保护更新、完整社区建设、公共空间提升、基础设施补短板、城市安全韧性提升、城市生态修复等。属性：scene_type、derivation_method（原文提取/语义归纳/人工标注/模型推理）"
+  PolicyTool: "具体政策工具：城市更新中用于实现治理目标的具体政策、制度、措施或治理手段。属性：tool_type（命令型/激励型/劝诫型/能力型/系统变革型）、mandatory_level（强制/引导/鼓励/支持/禁止/限制）、source_text"
+  ToolCategory: "政策工具类别：归类政策工具的分类节点。属性：classification_system（一般政策工具分类/城市更新工具分类）、urban_renewal_category（规划引导/土地配置/开发激励/财政金融/权益协调/实施管理/监督反馈）"
+  Procedure: "程序：审批、备案、评估、论证、公示、听证、入库、验收、监督、征收、补偿等行政或治理程序。属性：procedure_type、time_limit"
+  Obligation: "权利义务：法规规定的权利、义务、禁止或责任。属性：obligation_type（权利/义务/禁止/职责/鼓励/支持）、modality（应当/可以/不得/禁止/鼓励/支持/负责/依法）"
+  Condition: "适用条件：政策工具或程序适用时的前置条件。如'经批准后''符合XX条件'。属性：condition_type（规划条件/审批条件/权属条件/安全条件/环保条件/公众参与条件/程序条件/资金条件）"
+  Constraint: "约束条件：对行为设置的边界性、底线性或限制性要求。如'不得突破''严守''控制线'。属性：constraint_type（用途管制/空间边界/强制标准/历史保护/生态保护/权益保护/安全底线/公共利益）"
+  Penalty: "法律责任：违反法规后的处罚。属性：penalty_type（行政处罚/刑事处罚/民事责任/行政处分/信用惩戒/整改责任）、amount_or_measure"
+  TimePoint: "时间节点：生效、修订、废止、截止、过渡期等时间信息。属性：time_type（发布日期/生效日期/修订日期/废止日期/截止日期/过渡期）"
+  Region: "适用区域：全国、省、市、县、特定区域等。属性：level（全国/区域/省/市/县/乡镇街道/社区/特定区域）"
+
+relationship_type_prompts:
+  # 文档层次
+  has_chapter: "文档包含章"
+  has_section: "章包含节"
+  has_article: "文件/章/节包含条文"
+  has_clause: "条文包含款"
+  article_in_document: "条文或款属于某一法规文件"
+  # 法条依据
+  cites: "引用其他法规：如'根据《城乡规划法》第X条'、'依据《土地管理法》规定'、'按照国务院有关规定'"
+  implements: "实施上位法：如'为实施《城乡规划法》制定本办法'、'根据《土地管理法》授权'"
+  amends: "修正/修订：如'对《XX法》作如下修改'、'将第X条修改为'"
+  replaces: "替代/废止：如'本法自施行之日起，XX法同时废止'"
+  supplements: "补充规定：如'在XX基础上补充规定'"
+  basis_for_planning: "法规或条文作为规划编制、审批、实施或政策工具设立的依据"
+  # 主体关系
+  issued_by: "法规文件由某主体发布或制定"
+  implemented_by: "条文、政策工具、程序或义务由某主体负责实施"
+  assigned_to: "监管职责、管理职责、实施任务分配给某主体"
+  # 语义规制
+  regulates: "条文对某法规事项进行规制（准入、禁止、限制、鼓励、保护等）"
+  defines_object: "条文对法规事项、空间对象或更新场景进行定义或界定"
+  applies_to: "条文、程序或政策工具适用于某法规事项、空间对象、更新场景或区域"
+  sets_obligation: "条文设定权利、义务、禁止、职责或支持性要求"
+  sets_condition: "条文、政策工具或程序设置适用条件（前置条件）"
+  sets_constraint: "条文、政策工具或程序设置边界性、底线性或限制性要求"
+  prescribes_penalty: "条文规定了违法行为的法律后果"
+  # 政策工具
+  extracts_tool: "从条文中识别出具体政策工具"
+  belongs_to_category: "具体政策工具属于某类政策工具类别"
+  applies_to_scene: "政策工具适用于某类城市更新场景"
+  targets_object: "政策工具作用于某一法规事项或空间对象"
+  coordinates_with: "两个政策工具之间存在并列协同或组合使用关系"
+  supports_tool: "一个政策工具对另一个形成前置支撑或条件支撑"
+  # 程序
+  requires_procedure: "条文、政策工具或法规事项要求履行某类程序"
+  procedure_for: "某一程序对应某类法规事项、空间对象、更新场景或政策工具"
+  precedes_procedure: "一个程序在时序上先于另一个程序"
+  # 辅助
+  governs_region: "法规政策或条文适用于某一区域"
+  effective_timeline: "法规文件关联时间节点（发布/生效/修订/废止）"
+  standard_for: "标准、规范或条文适用于某一法规事项、空间对象、程序或政策工具"
+  article_effective_timeline: "条文关联时间节点（生效/截止/过渡期）"
+
+extraction_tips:
+  citation_patterns: "注意识别法条引用模式：'根据《XX法》'、'依照第X条规定'、'按照国务院XX规定'、'参照XX标准执行'"
+  article_classification: "法条类型判断：管理性（应当/必须）、禁止性（不得/禁止）、授权性（可以/有权）、程序性（申请/审批/备案）、处罚性（罚款/责令/没收）"
+  cross_reference: "特别注意跨文档引用：当条文引用其他法规时，创建cites关系并记录引用上下文"
+  entity_boundary_rules: |
+    实体边界规则（严格遵守）：
+    - LegalObject：法规事项，回答"管什么事项"，如规划编制、土地利用、财政支持
+    - SpatialObject：空间对象，回答"作用于什么空间"，如老旧小区、城中村、低效用地
+    - RenewalScene：更新场景，回答"用于什么更新场景"，如老旧小区改造、城中村改造
+    - Procedure：程序，强调流程步骤（审批/备案/评估/公示/验收/入库）
+    - PolicyTool：政策工具，强调治理手段、政策措施、制度安排或支持机制
+    - Obligation：权利义务，强调主体应当/可以/不得做什么
+    - Condition：适用条件，强调前置条件（经批准/符合/满足/具备）
+    - Constraint：约束条件，强调底线限制（不得突破/严守/控制线/强制性标准）
+  do_not_extract: |
+    - 不要新增本体之外的实体类型或关系类型
+    - 文本中没有依据时不要强行抽取
+    - conflicts_with和has_gap不纳入本阶段抽取

dofile/kg_project/config/legal_config.yaml

@@ -0,0 +1,86 @@
+project_name: "urban_planning_law_kg"
+project_description: "城市规划法律法规知识图谱构建"
+
+data:
+  source_dir: "E:\\Project\\SI\\2026_KG_PlanningLaw\\data\\城市规划法律法规\\城市更新法规数据库"
+  total_documents: 296
+  categories:
+    - {id: 0, name: "0知识图谱目录", type: "Index"}
+    - {id: 1, name: "1法律", type: "Law"}
+    - {id: 2, name: "2行政法规", type: "AdministrativeRegulation"}
+    - {id: 3, name: "3部门规章", type: "DepartmentalRule"}
+    - {id: 4, name: "4党中央国务院文件", type: "PolicyDocument"}
+    - {id: 5, name: "5国家主管部门文件", type: "PolicyDocument"}
+    - {id: 6, name: "6主要技术标准", type: "PolicyDocument"}
+  min_text_length: 50
+
+api:
+  config_file: "config/api_keys.yaml"
+  model: "deepseek-chat"
+  max_tokens: 8192
+  temperature: 0.0
+
+processing:
+  concurrent_requests: 5
+  max_retries: 3
+  retry_delay: 2
+  batch_size: 10
+
+paths:
+  config_dir: "config"
+  data_dir: "data"
+  output_dir: "output"
+  logs_dir: "logs"
+  ontology_dir: "ontology"
+  scripts_dir: "scripts"
+  src_dir: "src"
+
+ontology:
+  ontology_file: "ontology/legal_ontology.json"
+  entity_ontology_file: "config/legal_ontology.yaml"
+
+neo4j:
+  uri: "bolt://localhost:7687"
+  username: "neo4j"
+  password: "password"
+  database: "neo4j"
+
+extraction:
+  entity_types:
+    - Law
+    - AdministrativeRegulation
+    - DepartmentalRule
+    - PolicyDocument
+    - Chapter
+    - Section
+    - Article
+    - GovernmentBody
+    - LegalSubject
+    - SpatialConcept
+    - AdministrativeProcedure
+    - Obligation
+    - Penalty
+    - TimePoint
+    - Region
+  relation_types:
+    - cites
+    - implements
+    - amends
+    - replaces
+    - supplements
+    - issued_by
+    - implemented_by
+    - regulates
+    - defines_spatial
+    - requires_procedure
+    - sets_obligation
+    - prescribes_penalty
+    - applies_to
+    - governs_region
+  confidence_threshold:
+    entity: 0.8
+    relation: 0.7
+
+logging:
+  level: "INFO"
+  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"

dofile/kg_project/config/legal_ontology.yaml

@@ -0,0 +1,246 @@
+entity_types:
+  Law:
+    prefix: "LAW"
+    description: "全国人大及其常委会制定的法律"
+    required_attributes: [name]
+    optional_attributes:
+      - full_title
+      - promulgation_date
+      - effective_date
+      - status
+      - amendment_dates
+
+  AdministrativeRegulation:
+    prefix: "REG"
+    description: "国务院制定的行政法规"
+    required_attributes: [name]
+    optional_attributes:
+      - full_title
+      - promulgation_date
+      - effective_date
+      - status
+      - order_number
+
+  DepartmentalRule:
+    prefix: "RULE"
+    description: "各部委制定的部门规章"
+    required_attributes: [name]
+    optional_attributes:
+      - full_title
+      - promulgation_date
+      - effective_date
+      - status
+      - order_number
+
+  PolicyDocument:
+    prefix: "DOC"
+    description: "党中央/国务院/主管部门文件、技术标准"
+    required_attributes: [name]
+    optional_attributes:
+      - full_title
+      - issue_date
+      - document_number
+      - document_type
+      - status
+
+  Chapter:
+    prefix: "CH"
+    description: "法律文件的章"
+    required_attributes: [name, number]
+    optional_attributes:
+      - title
+
+  Section:
+    prefix: "SEC"
+    description: "法律文件的节"
+    required_attributes: [name, number]
+    optional_attributes:
+      - title
+
+  Article:
+    prefix: "ART"
+    description: "法律文件的具体条文"
+    required_attributes: [number, text]
+    optional_attributes:
+      - article_type
+
+  GovernmentBody:
+    prefix: "GOV"
+    description: "立法/行政/主管部门"
+    required_attributes: [name]
+    optional_attributes:
+      - full_name
+      - level
+      - type
+
+  LegalSubject:
+    prefix: "SUBJ"
+    description: "法律规制的事项或主体"
+    required_attributes: [name]
+    optional_attributes:
+      - category
+      - description
+
+  SpatialConcept:
+    prefix: "SPAT"
+    description: "国土空间规划中的空间概念"
+    required_attributes: [name]
+    optional_attributes:
+      - type
+      - definition
+
+  AdministrativeProcedure:
+    prefix: "PROC"
+    description: "规划/用地/建设的行政程序"
+    required_attributes: [name]
+    optional_attributes:
+      - type
+      - time_limit
+      - applicable_subjects
+
+  Obligation:
+    prefix: "OBL"
+    description: "法律条文规定的权利、义务或禁止"
+    required_attributes: [text]
+    optional_attributes:
+      - type
+
+  Penalty:
+    prefix: "PEN"
+    description: "违反法律规定的处罚"
+    required_attributes: [type, description]
+    optional_attributes:
+      - applicable_violation
+      - legal_basis
+
+  TimePoint:
+    prefix: "TIME"
+    description: "法规中提到的具体时间"
+    required_attributes: [description]
+    optional_attributes:
+      - year
+      - time_type
+
+  Region:
+    prefix: "REGION"
+    description: "法规适用的区域"
+    required_attributes: [name]
+    optional_attributes:
+      - level
+      - feature
+
+relationship_types:
+  has_chapter:
+    description: "包含章"
+    source_types: ["Law", "AdministrativeRegulation", "DepartmentalRule", "PolicyDocument"]
+    target_types: ["Chapter"]
+
+  has_section:
+    description: "包含节"
+    source_types: ["Chapter"]
+    target_types: ["Section"]
+
+  contains_article:
+    description: "包含条"
+    source_types: ["Chapter", "Section"]
+    target_types: ["Article"]
+
+  article_in_document:
+    description: "条属于文件"
+    source_types: ["Article"]
+    target_types: ["Law", "AdministrativeRegulation", "DepartmentalRule", "PolicyDocument"]
+
+  cites:
+    description: "引用其他法规"
+    source_types: ["Article", "PolicyDocument"]
+    target_types: ["Law", "AdministrativeRegulation", "DepartmentalRule"]
+
+  implements:
+    description: "实施/落实上位法"
+    source_types: ["PolicyDocument", "DepartmentalRule"]
+    target_types: ["Law", "AdministrativeRegulation"]
+
+  amends:
+    description: "修正/修订"
+    source_types: ["Law", "AdministrativeRegulation", "DepartmentalRule"]
+    target_types: ["Law", "AdministrativeRegulation", "DepartmentalRule"]
+
+  replaces:
+    description: "替代/废止"
+    source_types: ["Law", "AdministrativeRegulation", "DepartmentalRule"]
+    target_types: ["Law", "AdministrativeRegulation", "DepartmentalRule"]
+
+  supplements:
+    description: "补充"
+    source_types: ["PolicyDocument"]
+    target_types: ["Law", "AdministrativeRegulation", "DepartmentalRule"]
+
+  issued_by:
+    description: "发布机关"
+    source_types: ["Law", "AdministrativeRegulation", "DepartmentalRule", "PolicyDocument"]
+    target_types: ["GovernmentBody"]
+
+  implemented_by:
+    description: "实施机关"
+    source_types: ["Article", "AdministrativeProcedure"]
+    target_types: ["GovernmentBody"]
+
+  regulates:
+    description: "规制事项"
+    source_types: ["Article", "Obligation"]
+    target_types: ["LegalSubject"]
+
+  defines_spatial:
+    description: "界定空间概念"
+    source_types: ["Article"]
+    target_types: ["SpatialConcept"]
+
+  applies_to:
+    description: "适用于"
+    source_types: ["Article", "AdministrativeProcedure"]
+    target_types: ["LegalSubject"]
+
+  sets_obligation:
+    description: "定义务"
+    source_types: ["Article"]
+    target_types: ["Obligation"]
+
+  prescribes_penalty:
+    description: "规定处罚"
+    source_types: ["Article", "Obligation"]
+    target_types: ["Penalty"]
+
+  requires_procedure:
+    description: "要求程序"
+    source_types: ["Article"]
+    target_types: ["AdministrativeProcedure"]
+
+  procedure_for:
+    description: "程序对应事项"
+    source_types: ["AdministrativeProcedure"]
+    target_types: ["LegalSubject"]
+
+  governs_region:
+    description: "管辖区域"
+    source_types: ["Law", "AdministrativeRegulation", "DepartmentalRule"]
+    target_types: ["Region"]
+
+  effective_timeline:
+    description: "生效时间线"
+    source_types: ["Law", "AdministrativeRegulation", "DepartmentalRule"]
+    target_types: ["TimePoint"]
+
+  related_to:
+    description: "相关"
+    source_types: ["Any"]
+    target_types: ["Any"]
+
+  standard_for:
+    description: "标准适用于"
+    source_types: ["PolicyDocument"]
+    target_types: ["LegalSubject"]
+
+  category_index:
+    description: "分类索引"
+    source_types: ["Law", "AdministrativeRegulation", "DepartmentalRule", "PolicyDocument"]
+    target_types: ["LegalSubject"]